BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:On the Scalability of Main Memory OLTP Systems Under High Contenti
 on
DTSTART:20170626T090000
DTEND:20170626T110000
DTSTAMP:20260916T043450Z
UID:29723246db93256a999a473e5dce0c8947b11bb28c6ba5009dcff191
CATEGORIES:Conferences - Seminars
DESCRIPTION:Mustafa Iman\nEDIC candidacy exam\nExam president: Prof. Willy
  Zwaenepoel\nThesis advisor: Prof. Anastasia Ailamaki\nCo-examiner: Prof. 
 James Larus\n\nAbstract\nMain memory online transaction processing (OLTP) 
 engines achieve higher throughput than their disk based counterparts. They
  benefit from not having IO stalls. Main scalability bottleneck in these s
 ystems is concurrency control. Current state of the art concurrency contro
 l mechanisms are unable to scale to multiple cores under contented workloa
 ds. With soon to be arriving 1000-core machines\, this lack of scalability
  will be more visible.\n\nIn this report\, we discuss the scalability of m
 ain memory OLTP engines under contention. First\, we explain the architect
 ural changes to database systems with introduction of main memory OLTP sys
 tems. Then\, we discuss the scalability of these systems on multi-core mac
 hines. We use Silo as an example of near-linear scalable engine for low to
  medium contention. Then\, we discuss an extensive study on concurrency co
 ntrol with 1000-core machines. This shows that no known concurrency contro
 l scales well under high contention. Therefore\, we need to study the bott
 lenecks of current main memory OLTP engines to make them ready for many-co
 re systems.\n\nFinally\, we present our cache hierarchy aware approach to 
 improve scalability of concurrency control methods under high contention.\
 n\nBackground papers\nThe end of an architectural era:(it's time for a com
 plete rewrite)\, Stonebraker\, M.\, Madden\, S.\, Abadi\, et al.\nStaring 
 into the abyss: An evaluation of concurrency control with one thousand cor
 es\, Yu\, X.\, Bezerra\, G.\, et al.\nSpeedy transactions in multicore in-
 memory databases\, Tu\, S.\, Zheng\, W.\, et al.\n\n 
LOCATION:BC 229 https://plan.epfl.ch/?room==BC%20229
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR